© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7556
    Prev
    Next
    INDEX
    Explanations

    verb endings -ing, -ed

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on past-tense verb forms ending in “-ed.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ニャ
    0.57
    訲
    0.57
     лінії
    0.56
    幵
    0.56
    淐
    0.56
    䏹
    0.56
    敂
    0.55
    䧏
    0.55
    觡
    0.55
    нето
    0.54
    POSITIVE LOGITS
     Lour
    0.67
     it
    0.66
     Diese
    0.62
     Ihnen
    0.61
     Dieser
    0.61
     Lest
    0.60
     Bourke
    0.59
     Its
    0.58
     Weitere
    0.57
    มัน
    0.57
    Activations Density 0.000%

    No Known Activations